Reject a task by requesting Core T5 review of the active attempt; Core validates the evidence and advances the workflow.
Request Core T5 review to active; Core validates evidence and advances the attempt.
| Name | Required | Description | Default |
|---|---|---|---|
| actor | Yes | ||
| task_id | Yes | ||
| report_ref | Yes | ||
| review_ref | Yes | ||
| profile_ref | Yes | ||
| authorization_ref | Yes |
Changes observed during successful MCP inspections.
v4.0.5Input schema / properties / actor / defaultRemoved value: -"ADMIN"Input schema / properties / actor / descriptionRemoved value: -"Role code of the rejector (default ``\"ADMIN\"``)."Input schema / properties / authorization_refAdded value: +{
+ "type": "string"
+}Input schema / properties / noteRemoved value: -{
- "default": "",
- "description": "Mandatory rejection reason (strongly recommended).",
- "type": "string"
-}Input schema / properties / profile_refAdded value: +{
+ "type": "string"
+}Input schema / properties / report_refAdded value: +{
+ "type": "string"
+}Input schema / properties / review_refAdded value: +{
+ "type": "string"
+}Input schema / properties / task_id / descriptionRemoved value: -"Task ID or full filename."Input schema / requiredPrevious value: -[
- "task_id"
-]New value: +[
+ "task_id",
+ "actor",
+ "report_ref",
+ "review_ref",
+ "authorization_ref",
+ "profile_ref"
+]Output schema / (root)Previous value: -{
- "properties": {
- "result": {
- "type": "string"
- }
- },
- "required": [
- "result"
- ],
- "type": "object",
- "x-fastmcp-wrap-result": true
-}New value: +nullv3.2.4Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden, but it only vaguely references a Core T5 review workflow. It does not explain what rejection does, whether it is final, what permissions or authorization are required, or what side effects occur.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is short but cryptic rather than concise. Jargon such as 'Core T5', 'active', and 'attempt' is not front-loaded or explained, so the single sentence does not earn its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a six-parameter, fully required mutation-style tool with no annotations and no output schema, the description is completely inadequate. It does not explain the operation, the parameters, the authorization model, or the outcome.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has six required parameters with 0% description coverage, and the description explains none of them. Terms like report_ref, review_ref, authorization_ref, and profile_ref remain completely undefined.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The tool name says reject_task, but the description instead talks about requesting 'Core T5 review to active' and Core advancing the attempt. It does not clearly state that this tool rejects a task, nor does it distinguish the operation from sibling tools like approve_task or reopen_task.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool instead of approve_task, reopen_task, or other task-state tools. The description gives no conditions, prerequisites, or exclusions, so an agent cannot confidently choose it over alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.